Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 17139
    Prev
    Next
    INDEX
    Explanations

    specific days or dates

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days along with significant events related to them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hett
    -0.72
    olate
    -0.70
    ãģķ
    -0.69
    ierrez
    -0.69
    ãģĤ
    -0.66
     VIDEOS
    -0.63
    éļ
    -0.62
    ersen
    -0.61
    acus
    -0.60
    ãĤ´ãĥ³
    -0.60
    POSITIVE LOGITS
    lies
    0.79
    liest
    0.79
    nings
    0.73
    lights
    0.67
     Theresa
    0.65
    MAR
    0.65
    life
    0.65
    ultimate
    0.65
    iest
    0.65
    DAY
    0.64
    Activations Density 0.091%

    No Known Activations